Bruno J Neves1*, Rodolpho C Braga2, Cleber C Melo-Filho3, José Teofilo Moreira-Filho4, Eugene N Muratov5, Carolina Horta Andrade5 and PGR Achary5
1Laboratory for Molecular Modeling and Drug Design, Faculty of Pharmacy, Federal University of Goias, Goiania, Brazil
2Laboratory of Cheminformatics, Centro University of Anapolis, Brazil
3Laboratory for Molecular Modeling, Division of Chemical Biology and Medicinal Chemistry, University of North Carolina at Chapel Hill, United States
4Department of Chemical Technology, Odessa National Polytechnic University, Ukraine
5Department of Chemistry, Siksha O Anusandhan, India
*Corresponding Author: Bruno J Neves, Laboratory for Molecular Modeling and Drug Design, Faculty of Pharmacy, Federal University of Goias, Goiania, Brazil.
Received: December 27, 2021 Published: May 27, 2022
In the field of drug development, virtual screening (VS) has developed as a potent computer tool for screening huge libraries of small compounds for novel hits with desirable features that can subsequently be verified experimentally. Like that of other computational techniques, isn't to replace in vitro or in vivo experiments, but to speed up the discovery process minimize the number of candidates that must be examined experimentally, and justify their selection. Furthermore, because of its time, cost, resource, and labour savings, Virtual Screening has become quite popular in pharmaceutical businesses. Because of its high throughput and high hit rate, quantitative structure–activity relationship (QSAR) analysis is the most potent of the Virtual Screening techniques. Relevant chemogenomics data is acquired from databases and the literature as the initial stage in developing a QSAR model. In this mini review We outline and critically examine current advances in QSAR-based Virtual Screening in drug discovery and show how it may be used to find potential molecules with desired features . Every day, scientists and researchers all around the world create massive amounts of data; for example, more than 74 million molecules have been recorded in Chemical Abstract Services. According to a recent research, there are currently roughly 1060 compounds classed as novel drug-like molecules. The collection of such molecules is now referred to as "dark chemical space" or "dark chemistry." To examine such hidden molecules scientifically, a large number of live and updated databases (protein, cell, tissues, structure, medicines, and so on) are now accessible. The convergence of three distinct sciences: 'genomics,' 'proteomics,' and 'in-silico simulation,' will transform the drug development process. The screening of a large number of drug-like compounds is a difficult task that must be handled efficiently. Virtual screening (VS) is an essential computational technique in the drug discovery process; nevertheless, experimental drug verification is also vital in the drug development process. One machine learning approach that is often employed in VS techniques is quantitative structure-activity relationship (QSAR) analysis. The current mini-review focuses on the following topics: web-based machine learning tools, the role of QSAR in VS approaches, successful implementations of QSAR-based VS leading to drug discovery, and the benefits and limitations of QSAR .
Keywords: Computer-assisted Drug Design; Machine Learning; Cheminformatics; Molecular Descriptors; Virtual Screening
Citation: Bruno J Neves., et al. “QSAR-based Virtual Screening: Advances and Applications in Drug Discovery". Acta Scientific Pharmacology 3.6 (2022): 08-12.
Copyright: © 2022 Bruno J Neves., et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.